[bugfix] restore pr-7029 and fix patch error (#7294)

### What this PR does / why we need it?
This PR restores #7029, which adds W8A8C8 support for dsv3.2/glm5 using
the `lightning_indexer_quant` ops in the pd-mix stage.

The original PR was reverted by #7288 because the patch did not work
with the recompute scheduler.

This PR also fixes the patching issue so that it works correctly with
the recompute scheduler.

### Does this PR introduce _any_ user-facing change?
Yes. To enable LI C8, users need to set the `enable_sparse_c8` option to
`"true"` in `additional_config`.

- vLLM version: v0.17.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: rjg-lyh <1318825571@qq.com>

vllm_ascend/ascend_config.py

@@ -134,9 +134,12 @@ class AscendConfig:
             bool(additional_config.get("enable_async_exponential", False)) and not vllm_is_batch_invariant()
         )
 
+        use_sparse = hasattr(vllm_config.model_config, "hf_text_config") and hasattr(
+            vllm_config.model_config.hf_text_config, "index_topk"
+        )
+
         self.enable_kv_nz = additional_config.get("enable_kv_nz", False)
         if self.enable_kv_nz:
-            use_sparse = hasattr(vllm_config.model_config.hf_text_config, "index_topk")
             if not vllm_config.model_config.is_deepseek_mla or use_sparse:
                 raise RuntimeError("enable_kv_nz is only supported for mla currently.")
             if vllm_config.kv_transfer_config is None or not vllm_config.kv_transfer_config.is_kv_consumer:
@@ -144,6 +147,17 @@ class AscendConfig:
                     "enable_kv_nz is only supported in pd scenario and can only be used in D node."
                 )
 
+        from vllm_ascend.utils import AscendDeviceType, get_ascend_device_type
+
+        # Disable Sparse C8 for A5
+        # A5 has not been fully validated for this path and may carry hidden risks.
+        # TODO(rjg-lyh): Enable A5 support after sufficient validation.
+        self.enable_sparse_c8 = (
+            additional_config.get("enable_sparse_c8", False)
+            and use_sparse
+            and get_ascend_device_type() != AscendDeviceType.A5
+        )
+
     def _construct_weight_prefetch_config(self, additional_config):
         weight_prefetch_config = additional_config.get("weight_prefetch_config", {})
         self.weight_prefetch_config = WeightPrefetchConfig(weight_prefetch_config)